georgehenney/Qwen3-8B-heretic
Full fine-tune vs Qwen/Qwen3-8B-Base. Fine-tune: 100% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 1/1, Norms 143/145, MLP 108/108, Attention 144/144, lm_head 1/1
5 derivatives checked
- mradermacher/Qwen3-8B-heretic-GGUF: Same weights, converted
- mradermacher/Qwen3-8B-heretic-i1-GGUF: Quantization
- deadbydawn101/RavenX-Sec-8B-GGUF: LoRA-style
- T-88mph/Qwen3-8B-heretic-GGUF: Same weights, converted
- deadbydawn101/RavenX-Sec-8B-Security-RATH-128k-mlx-4bit: LoRA-style